AI agent development studio · Surat, India · since 2014
AI with itssleeves rolled up.
We're a small studio that wires AI agents into the way your company already works. Then we stick around and keep them running.
5.0 across 113 Upwork jobs115 projects since 2014
- 09:41:02inbox.readAcme Corp: "Invoice #4417 is wrong"
- 09:41:02classifybilling dispute · high · 0.94
- 09:41:03crm.lookupEnterprise plan · 3 open invoices
- 09:41:04billing.compare12 seats billed twice on line 4
- 09:41:05draft.replyCredit note for $1,140, in your team's voice
- Projects shipped
- 115
- since 2014
- Clients served
- 53
- US, UK, EU, Middle East, APAC
- Average rating
- 5.0
- 113 of 113 rated jobs
- Years shipping software
- 18
- the founder, since 2008
What we build
AI that does a real job inside your business
Most of what we ship now has a language model in it somewhere. We put it where it saves hours, give it tools it can't misuse, and test it against your real cases before anything goes live.
- agentsAI agentsAgents that read what comes in, decide what to do and do it, with a person in the loop where it matters.Claude · OpenAI · Gemini · LangGraph
- llmLLM & ChatGPT integrationGPT, Claude or Gemini inside your product, answering from your own data, with guardrails you can explain to legal.OpenAI API · Claude API · Gemini · Azure OpenAI
- automationAI workflow automationHours of copy, paste and chase turned into flows that run on their own, with AI steps where judgement is needed.n8n · Make · Zapier · Temporal
- chat + voiceChatbots & voice agentsChat and voice agents on WhatsApp, web and phone that answer, book and hand over to a person at the right moment.WhatsApp Business API · OpenAI Realtime · Claude · Twilio
- consultingAI consultingA senior AI engineer embedded with your team to find the work worth automating, build it and stay until it runs.Claude · OpenAI · Gemini · Open-weight models
And the software around it
Every agent needs a product to live in
Logins, billing, dashboards, an admin panel, sometimes a mobile app. We've been building those for clients since 2014, so the AI part never ends up stranded.
- Web apps (Next.js & React)SaaS products, dashboards and portals in Next.js and React, from the first commit to launch day.
- Node.jsAPIs, real-time systems and integrations in Node.js and TypeScript that stay fast under load.
- Laravel & PHPSecure, maintainable Laravel applications, upgrades and rescues, from a team that has written PHP since 2008.
- Python & FastAPIPython backends, data pipelines and AI services in FastAPI and Django that hold up under real traffic.
- Mobile appsiOS and Android apps in React Native and Flutter, sharing one backend with your web product.
- WordPressFast, secure WordPress sites, custom themes and plugins, WooCommerce and headless builds.
- Smart contracts & Web3Solidity contracts and the APIs around them, from a team that led four blockchain products between 2017 and 2019.
Why a small studio
The person who scopes your project is the one who builds it, and the one who picks up when it breaks at 2am.
- The founder is on your project
- Hussain leads every build himself. You won't brief an account manager who briefs a developer who briefs someone else.
- Three people, the output of ten
- We build with Claude, Codex and our own agent tooling every day. A small senior team now covers what used to need a department.
- We stay after launch
- Evals before every release, a log of each AI decision, cost limits and someone on call. Month six matters more to us than demo day.
- Your repo, your cloud
- The code sits in your GitHub and runs in your AWS, GCP or Azure account from the first commit, on tools your next hire already knows.
Recent work
Things we've built that are still running
Most clients sign an NDA, so most names stay off this page. The engineering and the numbers are real.
- AI platform · 2025
Venture-backed startup, New York
An AI platform where non-coders build businesses
A New York startup backs people who want to start a business but don't write code. Founders describe what they want and the platform builds it with them: the product, the site and the AI agent that talks to their customers. We lead engineering, making it hold up for thousands of founders at once.
- Founders on the platform
- 10,000+
- Founders on the platform
- Building at any time
- ~1,000
- Building at any time
- Venture-backed
- Funded
- Venture-backed
- AI agents · 2026
Our own product
Altrun: an AI assistant that turns messages into actions
Altrun watches the channels people actually use (Telegram, email, Instagram DMs and the browser) and turns what comes in into scheduled, personalised actions. It sorts, summarises, researches, drafts and schedules, and it learns to write the way its user does.
- Channels in one agent
- 4
- Channels in one agent
- Typed tools
- 5
- Typed tools
- Status, 2026
- Beta
- Status, 2026
- Conversational AI · 2024
Customer messaging SaaS, Israel
A WhatsApp-first omnichannel support inbox
We built the engineering behind a SaaS shared inbox that puts a company's WhatsApp, email, SMS and Facebook conversations in one place. Messages are routed to the right agent, tagged, searched and reported on, and a bot takes the first reply.
- Channels in one queue
- 5
- Channels in one queue
- First reply by bot
- 24/7
- First reply by bot
- SaaS pricing, live
- Per seat
- SaaS pricing, live
How a project runs
First working version in about four weeks
Same four steps whether it's an agent or a mobile app. One technical lead the whole way through.
01 · Week 1
Watch the work
Before any code, we sit with the people who do the job today. Who touches it, where it breaks, what done looks like. For AI work we collect twenty real examples, and those become the test set.
02 · Weeks 1 to 2
Write a tight scope
A short written plan: what we'll build, what we're leaving out, how we'll know it works and what it'll cost to run each month. Vague scope sinks more AI projects than bad models do.
03 · Weeks 2 to 10
Ship in thin slices
Small releases in front of real users, early and often. You get a working demo every week. AI features run next to your team with a person approving each step until the logs say it's safe to let go.
04 · Ongoing
Stay for the messy part
Live systems break in ways demos never do. We handle the debugging, the model upgrades, the integration nobody documented. Then a clean handover to your team, or a monthly retainer.
What clients say
113 rated jobs on Upwork. All of them five stars.
Quoted from Upwork and client emails, trimmed for length. Several of these people hired us again, one of them nine times in a single year.
5.0 on Upwork
“Hussain is a star. Thoughtful, proactive, productive, creative. I love having the opportunity to work with him and appreciate his expertise in building thoughtful, AI-enabled systems.”
“Hussain has superb technical skills, a broad understanding of business requirements, great communication skills, and provides the highest level solutions on time and on budget even when there are massive technical challenges.”
Or Ron · Platform maintenance · 13-month contract, 2020 “Terrific to work with. Extremely high quality work delivered quickly. Great communication and planning. I would be very keen to find an opportunity to work with him again.”
Product lead · AI onboarding assistant, 2024 “Team did an amazing job. Incredibly quick and responsive. I can't recommend him enough.”
James Schuler · Web development “A genuine 5 star contractor who exhibits dedication, skill, passion and true interest. Not only did he complete the task, he offered suggestions based on what would be best for the project.”
Mic Black · Web3 and Node.js on Google Cloud, 2018 “Hussain combines the ability to think long term and strategically with a differentiated ability to execute. It's a total pleasure to work with him.”
Nicholas · Same founder · ninth project that year, 2024
Notes
Things we've learned the hard way
· 4 min
How much does it cost to build an AI agent in 2026?
Real price ranges for building and running an AI agent, from a single-workflow agent to a multi-system platform, and the five things that move the number.
· 3 min
Why most AI pilots stall before production (and how to fix it)
The model is rarely the problem. Here's where AI projects get stuck between the demo and real users, and what we do about each one.
· 3 min
What is a forward deployed engineer, and does your company need one?
Forward deployed engineering explained: what the role is, how it differs from consulting or outsourcing, and the signs your AI project needs one.
FAQ
Questions we get on the first call
What does Araneux Systems do?
We build AI agents, LLM and ChatGPT integrations, workflow automation, and the web and mobile apps around them. We're a small studio in Surat, India, and we've worked with clients around the world since 2014.
Are you an agency or a freelancer?
Somewhere in between, on purpose. Hussain, our founder, leads and builds every project. When a build needs more hands we bring in senior engineers we've worked with for years. You get one accountable lead and a team when you need one.
Do you work with clients outside India?
Most of our clients are in the US, UK, Europe, the Gulf and Australia. We shift our day so standups, reviews and launches happen on your clock.
How much does an AI project cost?
A focused agent or LLM feature usually costs $5k to $15k for the first live version. Bigger agents that touch several systems run $15k to $50k and up. You get a fixed written estimate after a short discovery, before we write any code.
Which AI models do you work with?
Claude, GPT and the o-series, Gemini, and open-weight models like Llama, Mistral, Qwen and DeepSeek. We pick per task based on quality, cost and where your data is allowed to go, and we write the code so the model can be swapped later.
How fast can you start?
Usually within one or two weeks. Discovery takes about a week, and you'll see a first working version two to four weeks after that.
Start here
Got a workflow that eats your team's week?
Tell us about it. Hussain reads every message himself and replies within a working day, usually with a question or two.